Jun 2026· Science World· Vol 19, pp. 138-145· 0 citations· 18 references
TL;DR
A comparative analysis of the statistical and deep learning models for real-time, cell-level LTE eNodeB traffic forecasting across diverse geospatial environments using real-world data, with practical validation through LSTM- based traffic prediction for network optimization.
Abstract
Accurate short-term traffic prediction in Long-Term Evolution (LTE) networks is essential for proactive resource management and maintaining quality of service. With increasing data demand and dynamic traffic patterns, reliable forecasting at the cell level has become critical for efficient network operations. This analysis compared ARIMA, SARIMA, LSTM and GRU models with real hourly traffic data of urban and rural LTE eNodeBs in Nepal. The dataset was split chronologically into 80% training and 20% testing before preprocessing to prevent data leakage. The LSTM model performed best, achieving MSE of 1.4804, MAE of 0.8770, RMSE of 1.2167, and R-squared of 0.9563. Deep learning, particularly LSTM, was able to learn the non-linear and complex traffic patterns better than other models. This finding highlights the practical applicability of deep learning models in real world telecom network operations. The research provides a comparative analysis of the statistical and deep learning models for real-time, cell-level LTE eNodeB traffic forecasting across diverse geospatial environments using real-world data, with practical validation through LSTM- based traffic prediction for network optimization.
The rapid growth of Internet applications has led to increasingly complex network traffic, posing new challenges for accurate long-term forecasting. To address the limitations of traditional linear models in capturing nonlinear temporal dependencies, this paper proposes an improved TSM-Transformer model that introduces a Trend Attention module for long-term tendencies and a Seasonal Attention module for periodic variations. The model also optimizes encoder–decoder fusion to enhance information interaction. Experiments on the Traffic_One_Cell dataset demonstrate that the proposed model achieves the lowest MAE (1.2 × 10⁻3) and RMSE (2.9 × 10⁻3) with an R2 of 92.1%, outperforming ARIMA, GRU, and SVM baselines. The results confirm the model’s superiority in long-horizon network traffic prediction, providing reliable support for proactive resource allocation and network management.
Yuanxin Gao, Jianping Wu, Lei Liu et al.· 2026 IEEE International Conf...· 0 citations
In today's power industry, the ever-changing load environment makes accurate load forecasts even more important than ever. Even, day ahead load forecasting is crucial for the successful and efficient operation of the grid. With the absence of good reliable forecasts of daily load fluctuations, systems within the grid can become overloaded, resulting in a failure of the system, thus establishing the need for sound forecasting methods. As a solution to this challenge, different types of deep learning algorithms namely, Long Short-Term Memory, Bidirectional Long Short-Term Memory, Convolutional Neural Network based LSTM, Convolutional Neural Network based BiLSTM are applied for short-term load forecasting in this paper. The efficacy of the various deep learning techniques for short term load prediction is compared. The technique which produces the least value of root mean squared error between real and estimated load, is the most preferred one. The comparative analysis shows that Convolutional Neural Network based BiLSTM technique is a better option for short term load forecasting.
Unknown authors· ITEGAM- Journal of Engineeri...· 0 citations
Predicting electrical demand in distribution systems is a fundamental problem for the efficient operation of smart grids, especially under scenarios of high temporal variability. This study compares two multi-step forecasting strategies for 24-h horizons: a direct 24→24 strategy and a recursive strategy based on sequential 24→1 predictions. Four machine learning and deep learning architectures are evaluated: LSTM, N-HiTS, U-Net, and LightGBM, using real data from electrical feeders belonging to distribution systems in the equatorial region of Ecuador. The methodology includes constructing time windows, non-overlapping train/validation/test partitioning for evaluation, consistent normalization, and comparative analysis using MAE, RMSE, and MAPE metrics. The results show that the direct 24→24 strategy achieves the best overall performance, with LSTM standing out with an approximate MAPE of 4.12%. However, the recursive strategies exhibit greater stability in the face of atypical patterns observed during holidays and weekends. Furthermore, U-Net demonstrates competitive performance in both accuracy and temporal robustness, while LightGBM stands out for its computational efficiency. It is concluded that the selection of a forecasting strategy depends on the required balance between overall accuracy, temporal stability, and computational cost.
Erik Fernando Mendez-Garces, David Buldain, M. Comech· Energies· 0 citations
Accurate network traffic forecasting is fundamental to Quality of Service enforcement, proactive congestion control, and dynamic resource allocation in modern backbone and software-defined networks. However, existing approaches often lack adaptability to non-stationary traffic patterns and fail to provide a consistent comparative evaluation across diverse models under unified experimental conditions. This paper presents an adaptive, data-driven framework that integrates Bidirectional LSTM (Bi-LSTM), LSTM, Gated Recurrent Units (GRU), Random Forest, XGBoost, Support Vector Regression (SVR), and classical ARIMA regressors for short- and medium-term traffic forecasting. The proposed architecture couples multi-scale temporal feature extraction with a feedback-driven online retraining loop, enabling continuous adaptation to distributional shifts. Extensive experiments are conducted on two publicly available datasets CAIDA Equinix backbone traces and the MAWI traffic archive comprising over 72 hours of flow-level measurements at one-minute resolution. Bi-LSTM achieves the lowest RMSE of 0.0287 Gbps and the highest $R^{2}=0.9714$, outperforming ARIMA by $\mathbf{7 5 . 2 \%}$ and vanilla LSTM by $\mathbf{8 . 0 \%}$. All results are confirmed via paired Diebold-Mariano (DM) tests and Student’s t-tests $(p \lt 0.01)$. System inference latency of 2.3 ms per batch satisfies real-time SDN control-plane requirements. Code and preprocessing scripts will be made publicly available to ensure full reproducibility.
E. Chithra, G. C. Bharathi, Sankara Rao et al.· International Conference on...· 0 citations
Accurate short-term load forecasting is essential for efficient smart grid operation and demand-side energy management. Traditional statistical models often struggle to capture nonlinear and irregular residential electricity consumption patterns. This paper proposes a hybrid deep learning architecture combining Temporal Convolutional Networks (TCN) and Long Short-Term Memory (LSTM) networks for submeterlevel load forecasting. The model uses dilated causal convolutions to extract short-term temporal features, followed by LSTM units to capture long-term dependencies in energy consumption data. Data preprocessing includes normalization and slidingwindow sequence generation to convert historical load data into supervised learning samples. The model is evaluated using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) on both synthetically generated residential load profiles and the real-world UCI Household Electric Power Consumption dataset. The Hybrid TCN-LSTM model achieves an average RMSE of 0.0428 and MAE of 0.0317 on the synthetic dataset across 250 consumers and RMSE of 0.4551 kW with MAE of 0.2842 kW on the UCI dataset. Results demonstrate that the hybrid architecture effectively captures short-term fluctuations and longterm temporal dependencies, enabling reliable load forecasting for smart grid applications.
Kruthika Menta, K. M. V. Gowda, Prajeesha et al.· 2026 6th International Confe...· 0 citations
TAccurate short-term electricity consumption forecasting is essential for operational planning, reserve allocation, and energy management in modern power systems. This study investigates the performance of recurrent and hybrid attention-based deep learning architectures for short-term electricity consumption forecasting, a sase study in Togo. The proposed framework integrates electricity consumption, meteorological, demographic, and temporal information in order to capture both intrinsic temporal dependencies and exogenous influences affecting electricity demand. Four forecasting architectures were evaluated using a weekly temporal window of 168 hours: LSTM-only, LSTM-decoder, LSTM-attention, and a hybrid LSTM--Multi-Head Attention--LSTM model. The experiments included multi-seed evaluation, ablation study, robustness analysis, and statistical comparison using the Wilcoxon signed-rank test. The results show that all models achieved extremely high forecasting accuracy, with coefficients of determination exceeding 0.9998 and MAPE values below 0.004%. The hybrid architectures slightly improved average forecasting performance, while the standalone LSTM model remained highly competitive. The robustness analysis revealed strong sensitivity to noisy inputs but moderate degradation under missing-data conditions. Statistical analysis indicated that the performance differences between architectures were not statistically significant at the 5% level. Overall, the study demonstrates that recurrent deep learning architectures provide reliable and operationally relevant solutions for electricity consumption forecasting in highly structured energy demand series.
Séna Apeke, Yao Bokovi, K. Gbafa et al.· Science Journal of Energy En...· 0 citations